2 problems

Let $X\in\mathbb{R}^{p\times T}$ and $Y\in\mathbb{R}^{d\times T}$ be the training data matrices, let $\hat X\in\mathbb{R}^{p\times\hat T}$ and $\hat Y\in\mathbb{R}^{d\times\hat T}$…

In sketched matrix ridge regression, let the generalization error denote the prediction error on an unseen test sample. Generalization-error conjecture. The generalization error ca…